"Fine," David mumbled, picking at a loose thread on the sofa. He didn't want to look up, to meet Leo's gaze. The image of the little hamster, its tiny paws paddling furiously in its exercise ball, kept flashing through his mind.

He knew he'd been overly dramatic, exaggerating the mess, the noise, the potential for allergens. Leo, usually so boisterous, had retreated to his room after their argument, the silence from his usually chatty roommate creating a hollow ache in David’s chest.

He hated how small he felt now, how silly his reasons for refusing a pet seemed. He hadn't thought about Leo’s need for companionship. He'd only focused on himself. The thought of seeing the disappointment on Leo's face tomorrow as they both woke up was enough to make him queasy.

Emotion: ashamed

Cluster: Shame / Guilt
PC1 (Valence): -1.97 Negative
PC2 (Disposition): 1.06

Role in Research

This story is one of 1,000 stories generated for the emotion ashamed. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 ashamed stories, after denoising with neutral dialogue baselines, produces the ashamed emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the ashamed vector is projected through the unembedding matrix.

Promoted:
S0.376
ashamed0.344
ness0.327
0.297
😞0.295
Suppressed:
de-0.539
que-0.300
😍-0.288
(!)-0.269
🤩-0.242